A study of the ISOMAP algorithm and its applications in machine learning

Abstract

This project aims to study the foundations of nonlinear dimensionality reduction through manifold learning with the algorithm known as Isometric Feature Mapping (ISOMAP) and observe the application of the algorithm in practical experiments. The experiments were developed and executed in the following computational environment: Intel Core i7-4700MQ CPU 2.40GHz × 8, 16 GB of RAM. All the artifacts, (e.g., source-code, docs, experiments) can be found in the repository https://github.com/lucasdavid/manifold-learning and are licensed under the MIT License.